Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation
Abstract: Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target domain. To facilitate domain-invariant feature learning, existing methods typically mix data from both the source domain and target domain by simply copying and pasting the pixels. Such vanilla methods are usually sub-optimal since they do not take into account how well the mixed layouts correspond to real-world scenarios. Real-world scenarios are with an inherent layout. We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner. In particular, the framework contains a Depth-guided Contextual Filter (DCF) forndata augmentation and a cross-task encoder for contextual learning. DCF simulates the real-world layouts, while the cross-task encoder further adaptively fuses the complementing features between two tasks. Besides, it is worth noting that several public datasets do not provide depth annotation. Therefore, we leverage the off-the-shelf depth estimation network to generate the pseudo depth. Extensive experiments show that our proposed methods, even with pseudo depth, achieve competitive performance on two widely-used bench-marks, i.e. 77.7 mIoU on GTA→Cityscapes and 69.3 mIoU on Synthia→Cityscapes.
Primary Subject Area: [Content] Multimodal Fusion
Secondary Subject Area: [Content] Media Interpretation
Relevance To Conference: This article advances multimedia/multimodal processing by incorporating depth information with RGB images for semantic segmentation, enhancing model accuracy and robustness. It addresses domain adaptation challenges, making semantic segmentation more adaptable across different environments. This integration of multiple data types exemplifies the benefits of multimodal learning, significantly improving the understanding and processing of complex scenes in various applications.
Submission Number: 269
Loading